Upgrade to Encode 2.14

p4raw-id: //depot/perl@26863

diff --git a/MANIFEST b/MANIFEST
index 7f9225d..a7d1f20 100644 (file)
--- a/MANIFEST
+++ b/MANIFEST
@@ -590,6 +590,7 @@ ext/Encode/t/Encode.t               test script
 ext/Encode/t/encoding.t                test script
 ext/Encode/t/enc_utf8.t                test script
 ext/Encode/t/fallback.t                test script
+ext/Encode/t/from_to.t         test script
 ext/Encode/t/gb2312.enc                test data
 ext/Encode/t/gb2312.utf                test data
 ext/Encode/t/grow.t            test script

diff --git a/ext/Encode/AUTHORS b/ext/Encode/AUTHORS
index edb016c..60a7da0 100644 (file)
--- a/ext/Encode/AUTHORS
+++ b/ext/Encode/AUTHORS
@@ -53,7 +53,7 @@ Simon Cozens                  <simon@netthink.co.uk>
 Spider Boardman                        <spider@web.zk3.dec.com>
 Steve Hay                      <steve.hay@uk.radan.com>
 Steve Peters                   <steve@fisharerojo.org>
-Tatsuhiko Miyagawa             <miyagawa@edge.co.jp>
+Tatsuhiko Miyagawa             <miyagawa@bulknews.net>
 Tels                           <perl_dummy@bloodgate.com>
 Vadim Konovalov                        <vkonovalov@peterstar.ru>
 Yitzchak Scott-Thoennes                <sthoenna@efn.org>

diff --git a/ext/Encode/Changes b/ext/Encode/Changes
index acdead6..6cd82b7 100644 (file)
--- a/ext/Encode/Changes
+++ b/ext/Encode/Changes
@@ -1,8 +1,42 @@
 # Revision history for Perl extension Encode.
 #
-# $Id: Changes,v 2.12 2005/09/08 14:17:17 dankogai Exp dankogai $
+# $Id: Changes,v 2.14 2006/01/15 15:43:36 dankogai Exp dankogai $
 #
-$Revision: 2.12 $ $Date: 2005/09/08 14:17:17 $
+
+$Revision: 2.14 $ $Date: 2006/01/15 15:43:36 $
+2.14  2006/01/15 15:06:36 $
+! Makefile.PL 
+  Change 26295: Don't build manpages for Encode and Unicode::Normalize
+  Message-Id: <200512071540.jB7Fe4Gt017960@smtp3.ActiveState.com>
+! Encode.pm
+  Change 26081: Pod nit in Encode.pm, found by Marc Lehmann in RT #36949. 
+  Message-Id: <200511110357.jAB3vZcP023647@smtp3.ActiveState.com>
+! Encode.xs Encode/encode.h bin/enc2xs encengine.c
+  Change 25821: Mark more static Encode data structures as const.
+  Change 25823: use more 'const' in the Encode data structures.
+  Message-Id: <200510221243.j9MChTSu027711@smtp3.ActiveState.com>
+  Message-Id: <200510221343.j9MDhTk9001245@smtp3.ActiveState.com>
+
+2.13 2006/01/15 15:06:36
+! AUTHORS
+  Miyagawa's mail address updated
+  Message-Id: <693254b90601150535o767e10bai4f4732c275b4ebe0@mail.gmail.com>
+! lib/Encode/MIME/Header.pm
+  #16413: Encode::MIME::Headers patch to solve what is probably someone else's bug
+  http://rt.cpan.org/NoAuth/Bug.html?id=16413
+! lib/Encode/MIME/Header.pm t/mime-header.t
+  Applied: RT #16258: Support for RFC 2184 language tag
+  http://rt.cpan.org/NoAuth/Bug.html?id=16258
+! Encode.pm
+  Fixed RT #14559: fix for #8872 introduces new "bug"
+  http://rt.cpan.org/NoAuth/Bug.html?id=14559  
+! Encode.pm
++ t/from_to.t
+  from_to() now makes use of $check more naturally.
+  Message-Id: <693254b90601150535o767e10bai4f4732c275b4ebe0@mail.gmail.com>
+  <B10B4DE2-9BAF-4344-B3BE-2119977D817A@dan.co.jp>
+
+2.12 2005/09/08 14:17:17
 ! Encode.xs Encode.pm t/fallback.t
   Now accepts coderef for CHECK!
 ! ucm/8859-7.ucm

diff --git a/ext/Encode/Encode.pm b/ext/Encode/Encode.pm
index 4a4411b..7785f5a 100644 (file)
--- a/ext/Encode/Encode.pm
+++ b/ext/Encode/Encode.pm
@@ -1,9 +1,9 @@
 #
-# $Id: Encode.pm,v 2.12 2005/09/08 14:17:17 dankogai Exp dankogai $
+# $Id: Encode.pm,v 2.14 2006/01/15 15:43:36 dankogai Exp dankogai $
 #
 package Encode;
 use strict;
-our $VERSION = sprintf "%d.%02d", q$Revision: 2.12 $ =~ /(\d+)/g;
+our $VERSION = sprintf "%d.%02d", q$Revision: 2.14 $ =~ /(\d+)/g;
 sub DEBUG () { 0 }
 use XSLoader ();
 XSLoader::load(__PACKAGE__, $VERSION);
@@ -183,11 +183,10 @@ sub from_to($$$;$)
        require Carp;
        Carp::croak("Unknown encoding '$to'");
     }
-    my $uni = $f->decode($string,$check);
-    return undef if ($check && length($string));
-    $string =  $t->encode($uni,$check);
+    my $uni = $f->decode($string);
+    $_[0] = $string =  $t->encode($uni,$check);
     return undef if ($check && length($uni));
-    return defined($_[0] = $string) ? length($string) : undef ;
+    return defined($_[0]) ? length($string) : undef ;
 }
 
 sub encode_utf8($)
@@ -200,6 +199,7 @@ sub encode_utf8($)
 sub decode_utf8($;$)
 {
     my ($str, $check) = @_;
+    return $str if is_utf8($str);
     if ($check){
        return decode("utf8", $str, $check);
     }else{

diff --git a/ext/Encode/Encode.xs b/ext/Encode/Encode.xs
index 274fae0..6cc4a6a 100644 (file)
--- a/ext/Encode/Encode.xs
+++ b/ext/Encode/Encode.xs
@@ -1,5 +1,5 @@
 /*
- $Id: Encode.xs,v 2.6 2005/09/08 14:17:17 dankogai Exp dankogai $
+ $Id: Encode.xs,v 2.7 2006/01/15 15:43:36 dankogai Exp dankogai $
  */
 
 #define PERL_NO_GET_CONTEXT

diff --git a/ext/Encode/MANIFEST b/ext/Encode/MANIFEST
index 35aefdd..d54232f 100644 (file)
--- a/ext/Encode/MANIFEST
+++ b/ext/Encode/MANIFEST
@@ -72,6 +72,7 @@ t/enc_module.t        test script
 t/enc_utf8.t   test script
 t/encoding.t   test script
 t/fallback.t   test script
+t/from_to.t    test script
 t/gb2312.enc   test data
 t/gb2312.utf   test data
 t/grow.t       test script

diff --git a/ext/Encode/META.yml b/ext/Encode/META.yml
index 9373f60..fa6e843 100644 (file)
--- a/ext/Encode/META.yml
+++ b/ext/Encode/META.yml
@@ -1,7 +1,7 @@
 # http://module-build.sourceforge.net/META-spec.html
 #XXXXXXX This is a prototype!!!  It will change in the future!!! XXXXX#
 name:         Encode
-version:      2.12
+version:      2.14
 version_from: Encode.pm
 installdirs:  perl
 requires:

diff --git a/ext/Encode/bin/enc2xs b/ext/Encode/bin/enc2xs
index 82ff01c..7930ece 100644 (file)
--- a/ext/Encode/bin/enc2xs
+++ b/ext/Encode/bin/enc2xs
@@ -9,7 +9,7 @@ use strict;
 use warnings;
 use Getopt::Std;
 my @orig_ARGV = @ARGV;
-our $VERSION  = do { my @r = (q$Revision: 2.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION  = do { my @r = (q$Revision: 2.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 # These may get re-ordered.
 # RAW is a do_now as inserted by &enter

diff --git a/ext/Encode/encoding.pm b/ext/Encode/encoding.pm
index d0b083a..4db0401 100644 (file)
--- a/ext/Encode/encoding.pm
+++ b/ext/Encode/encoding.pm
@@ -1,4 +1,4 @@
-# $Id: encoding.pm,v 2.2 2005/09/08 14:17:17 dankogai Exp dankogai $
+# $Id: encoding.pm,v 2.2 2005/09/08 14:17:17 dankogai Exp $
 package encoding;
 our $VERSION = do { my @r = (q$Revision: 2.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 

diff --git a/ext/Encode/lib/Encode/CN/HZ.pm b/ext/Encode/lib/Encode/CN/HZ.pm
index fbc6ba6..94b372c 100644 (file)
--- a/ext/Encode/lib/Encode/CN/HZ.pm
+++ b/ext/Encode/lib/Encode/CN/HZ.pm
@@ -3,7 +3,7 @@ package Encode::CN::HZ;
 use strict;
 
 use vars qw($VERSION);
-$VERSION = do { my @r = (q$Revision: 2.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+$VERSION = do { my @r = (q$Revision: 2.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use Encode qw(:fallbacks);
 
@@ -45,6 +45,7 @@ sub decode ($$;$)
            }
        }
        else { # GB mode; the byte ranges are as in RFC 1843.
+           no warnings 'uninitialized';
            if ($str =~ s/^((?:[\x21-\x77][\x21-\x7E])+)//) {
                $ret .= $GB->decode($1, $chk);
            }

diff --git a/ext/Encode/lib/Encode/MIME/Header.pm b/ext/Encode/lib/Encode/MIME/Header.pm
index f4e2ad6..29fc858 100644 (file)
--- a/ext/Encode/lib/Encode/MIME/Header.pm
+++ b/ext/Encode/lib/Encode/MIME/Header.pm
@@ -1,7 +1,7 @@
 package Encode::MIME::Header;
 use strict;
 # use warnings;
-our $VERSION = do { my @r = (q$Revision: 2.1 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 2.2 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 use Encode qw(find_encoding encode_utf8 decode_utf8);
 use MIME::Base64;
 use Carp;
@@ -47,10 +47,15 @@ sub decode($$;$){
     $str =~ s/\?=\s+=\?/\?==\?/gos;
     # multi-line header to single line
     $str =~ s/(:?\r|\n|\r\n)[ \t]//gos;
+
+    1 while ($str =~ s/(\=\?[0-9A-Za-z\-_]+\?[Qq]\?)(.*?)\?\=\1(.*?)\?\=/$1$2$3\?\=/);  # Concat consecutive QP encoded mime headers
+                                                                                        # Fixes breaking inside multi-byte characters
+
     $str =~
        s{
            =\?                  # begin encoded word
                ([0-9A-Za-z\-_]+) # charset (encoding)
+                (?:\*[A-Za-z]{1,8}(?:-[A-Za-z]{1,8})*)? # language (RFC 2231)
                \?([QqBb])\?     # delimiter
                (.*?)            # Base64-encodede contents
                \?=              # end encoded word      
@@ -96,6 +101,7 @@ my $re_encoded_word =
        (?:
        =\?               # begin encoded word
        (?:[0-9A-Za-z\-_]+) # charset (encoding)
+        (?:\*\w+(?:-\w+)*)? # language (RFC 2231)
        \?(?:[QqBb])\?      # delimiter
        (?:.*?)             # Base64-encodede contents
        \?=                 # end encoded word

diff --git a/ext/Encode/t/from_to.t b/ext/Encode/t/from_to.t
new file mode 100644 (file)
index 0000000..dd1d9ec
--- /dev/null
+++ b/ext/Encode/t/from_to.t
@@ -0,0 +1,12 @@
+# $Id: from_to.t,v 1.1 2006/01/15 15:06:36 dankogai Exp $
+use strict;
+use Test::More tests => 3;
+use Encode qw(encode from_to);
+
+my $foo = encode("utf-8", "\x{5abe}");
+from_to($foo, "utf-8" => "latin1", Encode::FB_HTMLCREF);
+ok !Encode::is_utf8($foo);
+is $foo, '媾';
+
+my $bar = encode("latin-1", "\x{5abe}", Encode::FB_HTMLCREF);
+is $bar, '媾';

diff --git a/ext/Encode/t/mime-header.t b/ext/Encode/t/mime-header.t
index 5f80347..4e3ac56 100644 (file)
--- a/ext/Encode/t/mime-header.t
+++ b/ext/Encode/t/mime-header.t
@@ -1,5 +1,5 @@
 #
-# $Id: mime-header.t,v 2.0 2004/05/16 20:55:19 dankogai Exp $
+# $Id: mime-header.t,v 2.1 2006/01/15 15:06:36 dankogai Exp $
 # This script is written in utf8
 #
 BEGIN {
@@ -23,7 +23,7 @@ no utf8;
 
 use strict;
 #use Test::More qw(no_plan);
-use Test::More tests => 10;
+use Test::More tests => 11;
 use_ok("Encode::MIME::Header");
 
 my $eheader =<<'EOS';
@@ -55,6 +55,16 @@ EOS
 
 is(Encode::decode('MIME-Header', $uheader), $dheader, "decode UTF-8 (RFC2047)");
 
+my $lheader =<<'EOS';
+From: =?US-ASCII*en-US?Q?Keith_Moore?= <moore@cs.utk.edu>
+To: =?ISO-8859-1*da-DK?Q?Keld_J=F8rn_Simonsen?= <keld@dkuug.dk>
+CC: =?ISO-8859-1*fr-BE?Q?Andr=E9?= Pirard <PIRARD@vm1.ulg.ac.be>
+Subject: =?ISO-8859-1*en?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?=
+ =?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?=
+EOS
+
+is(Encode::decode('MIME-Header', $lheader), $dheader, "decode language tag (RFC2231)");
+
 
 $dheader=<<'EOS';
 From: 小飼 弾 <dankogai@dan.co.jp>

diff --git a/ext/Encode/ucm/8859-7.ucm b/ext/Encode/ucm/8859-7.ucm
index 69eab84..4dd4c6a 100644 (file)
--- a/ext/Encode/ucm/8859-7.ucm
+++ b/ext/Encode/ucm/8859-7.ucm
@@ -1,5 +1,5 @@
 #
-# $Id: 8859-7.ucm,v 2.1 2005/09/08 14:17:17 dankogai Exp dankogai $
+# $Id: 8859-7.ucm,v 2.1 2005/09/08 14:17:17 dankogai Exp $
 #
 # Original table can be obtained at
 # http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT